symphony-trello: Skill for Codex

.codex/skills/issue-sweep/SKILL.md

issue-sweep is a skill for Codex from martin-francois/symphony-trello. It costs 67 tokens per session (853 once invoked), scanned A, original, Apache-2.0.

A repository-wide process for reviewing open GitHub issues, which are tracked software tasks or reports, for quality and current relevance.

In plain words
What is it for?
Fetching all open issues and related pull requests, applying the project's triage policy, updating issue details and labels, and repeating checks until a full review finds no further changes.
Why use it?
It finds stale, duplicated, incorrectly labeled, dependent, or already completed issues instead of checking only a few examples.

Skill for Codex

Written for Codex: agents/openai.yaml present.

This is martin-francois/symphony-trello's own configuration. It tells Codex how to work on symphony-trello itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything symphony-trello configures →

Reuse

Borrowing it

Nothing to install: this file belongs to martin-francois/symphony-trello. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/martin-francois/symphony-trello/main/.codex/skills/issue-sweep/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/martin-francois/symphony-trello

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for issue-sweep

README.md
[![agentmods](https://agentmods.dev/badge/skills/martin-francois/symphony-trello/issue-sweep/github.svg)](https://agentmods.dev/skills/martin-francois/symphony-trello/issue-sweep)
Your own site
<a href="https://agentmods.dev/skills/martin-francois/symphony-trello/issue-sweep"><img src="https://agentmods.dev/badge/skills/martin-francois/symphony-trello/issue-sweep/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for issue-sweep

Your own site · 80×15
<a href="https://agentmods.dev/skills/martin-francois/symphony-trello/issue-sweep"><img src="https://agentmods.dev/badge/skills/martin-francois/symphony-trello/issue-sweep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 853 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00067 $0.00853
Opus 5.5 $0.00027 $0.00341
Sonnet 5.5 $0.00013 $0.00171
Haiku 4.5 $0.00007 $0.00085

Measured 6d ago against content hash d4ed4c0f74da, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

issue-sweep scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.codex/skills/issue-sweep/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Issue Sweep

This skill is a thin dispatcher. The canonical policy lives in ../../../docs/agents/github-issue-triage.md; do not duplicate the label matrix or issue editing rules here.

Workflow

  1. Read ../../../docs/agents/github-issue-triage.md completely before fetching or editing issues. Treat it as the source of truth for sweep scope, issue-body updates, labels, dependencies, compatibility decisions, and already-implemented checks.
  2. Confirm GitHub authentication and repository context with the active repository-approved GitHub tooling, such as the helper or app named by .tessl/RULES.md and installed GitHub skills. Do not use direct gh where those rules require helper or app access. If authentication is missing or editing is not permitted, report the blocker and do not pretend the sweep was completed.
  3. Fetch all open issues, including title, body, labels, milestone, assignees, assignment timeline events, linked or referencing open pull requests, and relevant comments. Do not limit the sweep to examples named by the user.
  4. Apply the canonical triage document in cycles. After making any change, fetch the open issue set again and repeat until one full pass finds no body, label, milestone, dependency, already-implemented, or relationship changes.
  5. Write every issue you create or whose body you rewrite through the Issue forms section of ../../../docs/agents/github-issue-triage.md, and create follow-up issues before the final audit run so it covers them.
  6. Handle comments by people on open and closed issues, pull requests, and Discussions as the canonical triage document's sweep rules say: reply, react, hide spam, answer paid-help and bounty offers, and post stale-assignment check-ins. Leave comments that need a maintainer decision for the report.
  7. Prefer editing maintainer-authored issue bodies over adding comments, unless the canonical triage document calls for a historical comment or the issue was opened by another account.
  8. End the sweep with the label audit from the repository root: node scripts/audit-issue-labels.ts. Fix every failure and rerun it until it reports none, then decide every judgment item as the canonical triage document's Label audit section says. The audit checks only the mechanical label rules; it does not replace step 4.
  9. Finish with a concise report: number of cycles, issues changed, issues intentionally left unchanged, labels or dependencies repaired, users assigned from pickup comments, replies posted (person and comment URL), comments that got a 👍 instead of a reply, spam comments and bodies with their authors, comments left for the maintainer and the decision each needs, stale assigned issues with no open pull request and whether a check-in was posted, issues closed as already implemented, the final label audit output with the decision for each judgment item, and any blockers.

Read the full file on GitHub · 74 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago Changed · +14 lines d4ed4c0f74da
  2. 2mo ago First seen · 60 lines · 67 tokens per session scan A e1e509d774cb

Subscribe to this mod's changes

issue-sweep is a skill published in the GitHub repository martin-francois/symphony-trello (5 stars, last pushed today), licensed Apache-2.0. It adds 67 tokens to every session and 853 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

issue-sweep compared with skills from other repositories

issue-sweep next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
issue-sweepmartin-francois/symphony-trelloSkill5todayApache-2.0A67Codex
assimilate-popular-workflowsa5c-ai/babysitterSkill1.9k5d agoMITA110Claude Code
mcp-app-verificationa5c-ai/babysitterSkill1.9k5d agoMITA48Claude Code
guardrails-ai-setupa5c-ai/babysitterSkill1.9k5d agoMITA30Claude Code
mcp-host-styling-integrationa5c-ai/babysitterSkill1.9k5d agoMITA44Claude Code
frontmatter-parsinga5c-ai/babysitterSkill1.9k5d agoMITA40Claude Code
rag-hybrid-searcha5c-ai/babysitterSkill1.9k5d agoMITA28Claude Code